Simon Willison’s Weblog

Twitter pranksters derail GPT-3 bot with newly discovered “prompt injection” hack. I’m quoted in this Ars Technica article about prompt injection and the Remoteli.io Twitter bot.

Posted 16th September 2022 at 6:33 pm

Recent articles

First impressions of Claude Cowork, Anthropic's general agent - 12th January 2026
My answers to the questions I posed about porting open source code with LLMs - 11th January 2026
Fly's new Sprites.dev addresses both developer sandboxes and API sandboxes at the same time - 9th January 2026

security 573 twitter 160 gpt-3 67 openai 383 prompt-engineering 176 prompt-injection 142 generative-ai 1578 llms 1544 press-quotes 21

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe